qra/manuscript/tex2word/preprocess_tex_for_word.py

#!/usr/bin/env python3
import re
import sys
from pathlib import Path

if len(sys.argv) != 3:
    print("Usage: preprocess_tex_for_word.py input.tex output.tex", file=sys.stderr)
    sys.exit(1)

src = Path(sys.argv[1]).read_text(encoding="utf-8")
text = src

# Rename \includegraphics{file.ext} -> \includegraphics{file.png}
text = re.sub(
    r'(\\includegraphics(?:\[[^\]]*\])?\{[^{}]+?)\.[^./{}\\]+(\})',
    r'\1.png\2',
    text
)

# Replace siunitx S[...] columns with plain right-aligned columns
text = re.sub(r'S\[[^\]]*\]', 'r', text)

# Replace bare S columns with r as well
text = re.sub(r'(?<![A-Za-z])S(?![A-Za-z])', 'r', text)

# Remove \resizebox{...}{...}{ ...tabular... }
# Allow optional % after opening { and before closing }
resizebox_tabular = re.compile(
    r'''
    \\resizebox\s*
    \{[^{}]*\}\s*              # first arg
    \{[^{}]*\}\s*              # second arg
    \{\s*%?\s*                 # opening body, optional %
    (\\begin\{tabular\}.*?\\end\{tabular\})   # inner tabular
    \s*%?\s*\}                 # optional % before closing }
    ''',
    re.DOTALL | re.VERBOSE
)

while True:
    new_text, n = resizebox_tabular.subn(r'\1', text)
    text = new_text
    if n == 0:
        break

Path(sys.argv[2]).write_text(text, encoding="utf-8")